Exploring and Analyizing Wine Enthusiast Reviews

Prerequisites

Load required packages

library(tidyverse)
library(ggplot2)
library(rtweet)
library(readr)

Dataset

Import processed data, which can be found here.

#read preprocessed data
wines <- read.csv(file = '../data/processed_data/wines.csv')

Get sample of dataset

#set seed value to birthday of Ricardo Rodriguez, American wrestler and ring announcer and Dr. Reinaldo (Rei) Sanchez-Arias
set.seed(19630217)

#set percentage to test with for simplicity
percentage <- 5
wine_sample<- sample_n(wines, percentage/100*nrow(wines))

Split Taster data into different Data Frame

tasters <- wines %>%
  select(taster_name, taster_twitter_handle) %>% unique()
tasters

Drop taster_twitter_handle in wines dataframe

wines <- wines %>%
  select(-taster_twitter_handle)
head(wines)

Add Rating Classification

Add following classification to wine dataset as found on the website:

Category	Rating	Description
Classic	98-100	The pinnacle of quality.
Superb	94-97	A great achievement.
Excellent	90-93	Highly recommended.
Very Good	87-89	Often good value; well recommended.
Good	83-86	Suitable for everyday consumption; often good value.
Acceptable	80-82	Can be employed in casual, less-critical circumstances

# function to add rating
rating_category <- function(points){
  if(points>=98){
    return("Classic")
  }
  else if (points>=94){
    return("Superb")
  }
  else if(points>=90){
    return("Excellent")
  }
  else if(points>=87){
    return("Very Good")
  }
  else if(points>=83){
    return("Good")
  }
  else{
    return("Acceptable")
  }
}

wines<- wines %>%
  rowwise() %>%
  mutate(rating_category = rating_category(points))
head(wines)

Explore the Data

EDA (correlation priceXpoints, with DataExplorer library? using (this)[https://datascienceplus.com/blazing-fast-eda-in-r-with-dataexplorer/])

wines %>% 
  ggplot() +
    geom_point(mapping = (aes(x = points, y = price)), na.rm = T)

wines %>%
    summarize(avg_price = mean(price, na.rm=TRUE), 
              sd_price = sd(price, na.rm=TRUE),
              lowest_price = min(price, na.rm=TRUE),
              highest_price = max(price,na.rm=TRUE))

wines %>%
    summarize(avg_points = mean(points, na.rm=TRUE), 
              sd_points = sd(points, na.rm=TRUE),
              lowest_points = min(points, na.rm=TRUE),
              highest_points = max(points,na.rm=TRUE))

Select the provinces based on points and Select the best province for wine based on the average points of the sample size.

#find the average number of points across the 1,000 samples

wine_per_province <- wine %>% 
  select(province, points) %>% 
  summarise(points = mean(points))
wine_per_province

#Find the best province for wine using the average points across the 1,000 samples #drop the descriptions or just select price? set points to max(points)

best_province <- wine_sample %>% 
  group_by(province, points) %>% 
  filter(points > 88.669)
best_province  

Rating distribution

Best wine, by variety

#wine_best_variety <- 
wines %>% 
  group_by(variety) %>% 
  summarise(mean_points = mean(points)) %>% 
  arrange(desc(mean_points)) 
  

user_price <- readline(prompt = "How much are you willing to spend on a bottle?")
user_price <- as.integer(user_price)

wines %>% 
  filter(price <= user_price) %>% 
  arrange(desc(points)) %>% 
  select(title, price, points)

Conclusion